Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “PHYSICAL FITNESS”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 631 records · Page 35
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Fringing Analysis and Simulation for the Vera C. Rubin Observatory’s Legacy Survey of Space and Time

Abstract The presence of fringing in astronomical Charge-Coupled Device (CCD) images will have an impact on photometric quality and measurements. Yet its impact on the Vera C. Rubin Observatory’s Legacy Survey of Space and Time (LSST) has not been fully studied. We present a detailed study on fringing for CCDs already implemented on the Rubin Observatory LSST Camera’s focal plane. After making physical measurements and knowing the compositions, we developed a model for the e2v CCDs. We present a method to fit for the internal height variation of the epoxy layer within the sensors based on fringing measurements in a laboratory setting. This method is generic enough that it can be easily modified to work for other CCDs. Using the derived fringing model, we successfully reproduce comparable fringing amplitudes that match the observed levels in images taken by existing telescopes with different optical designs. This model is then used to forecast the expected level of fringing in a single LSST y -band sky background exposure with Rubin telescope optics in the presence of a realistic time-varying sky spectrum. The predicted fringing amplitude in LSST images ranges from 0.04% to 0.2% depending on the location of a CCD on the focal plane. We find that the predicted variation in surface brightness caused by fringing in LSST y -band sky background images is about 0.6 μ Jy arcsec − 2 , which is 40 times larger than the current measurement error. We conclude that it is necessary to include fringing correction in the Rubin’s LSST image processing pipeline.

Astronomy & Astrophysics↗
DOE OSTI2024

Extraction of the neutron F 2 structure function from inclusive proton and deuteron deep-inelastic scattering data

The available world deep-inelastic scattering (DIS) data on proton and deuteron structure functions F 2 p , F 2 d , and their ratios are leveraged to extract the free neutron F 2 n structure function, the F 2 n / F 2 p ratio, and associated uncertainties using the latest nuclear effect calculations in the deuteron. Special attention is devoted to the normalization of the proton and deuteron experimental datasets and to the treatment of correlated systematic errors, as well as the quantification of procedural and theoretical uncertainties. The extracted F 2 n dataset is utilized to evaluate the Q 2 dependence of the Gottfried sum rule and the nonsinglet F 2 p − F 2 n moments. To facilitate replication of our study, as well as for general applications, we provide a comprehensive DIS database including all recent Jefferson Lab 6 GeV measurements, the extracted F n 2 , a modified CTEQ-JLab global parton distribution function fit named CJ15nlo_mod, and grids with calculated proton, neutron, and deuteron DIS structure functions. Published by the American Physical Society 2024

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
NASA NTRS1985

Models of the upper atmosphere

Several computer models of the thermosphere are discussed. J70MM, the Jacchia 1970 model with matrix and matrix mean output, and J703X, the Jacchia 1970, 1971, and 1977 models, are of primary interest. The subroutines in these programs were studied in detail, and several mistakes were found and corrected. It is proposed that a weighted average of the three-hour geomagnetic index be used in the models rather than a single index value. The densities (for a given date and time) generated by the J703X program (all three models), using both a single value of the index and weighted averages for three different lag times, are tabulated and discussed. Most of the equations used in the models are the results of empirical curve fits. An attempt was made to generate a theoretical prediction of the thermospheric temperature profile based on a simple physical model of atmospheric heat conduction in a spherically-symmetric shell. The exponential heating theory and the temperature dependence of k are discussed.

Davis, T. M.↗
NASA NTRS1997

Evolutionary Design of Controlled Structures

Basic physical concepts of structural delay and transmissibility are provided for simple rod and beam structures. Investigations show the sensitivity of these concepts to differing controlled-structures variables, and to rational system modeling effects. An evolutionary controls/structures design method is developed. The basis of the method is an accurate model formulation for dynamic compensator optimization and Genetic Algorithm based updating of sensor/actuator placement and structural attributes. One and three dimensional examples from the literature are used to validate the method. Frequency domain interpretation of these controlled structure systems provide physical insight as to how the objective is optimized and consequently what is important in the objective. Several disturbance rejection type controls-structures systems are optimized for a stellar interferometer spacecraft application. The interferometric designs include closed loop tracking optics. Designs are generated for differing structural aspect ratios, differing disturbance attributes, and differing sensor selections. Physical limitations in achieving performance are given in terms of average system transfer function gains and system phase loss. A spacecraft-like optical interferometry system is investigated experimentally over several different optimized controlled structures configurations. Configurations represent common and not-so-common approaches to mitigating pathlength errors induced by disturbances of two different spectra. Results show that an optimized controlled structure for low frequency broadband disturbances achieves modest performance gains over a mass equivalent regular structure, while an optimized structure for high frequency narrow band disturbances is four times better in terms of root-mean-square pathlength. These results are predictable given the nature of the physical system and the optimization design variables. Fundamental limits on controlled performance are discussed based on the measured and fit average system transfer function gains and system phase loss.

Masters, Brett P.↗
NASA NTRS2003

Oxygen-Partial-Pressure Sensor for Aircraft Oxygen Mask

A device that generates an alarm when the partial pressure of oxygen decreases to less than a preset level has been developed to help prevent hypoxia in a pilot or other crewmember of a military or other high-performance aircraft. Loss of oxygen partial pressure can be caused by poor fit of the mask or failure of a hose or other component of an oxygen distribution system. The deleterious physical and mental effects of hypoxia cause the loss of a military aircraft and crew every few years. The device is installed in the crewmember s oxygen mask and is powered via communication wiring already present in all such oxygen masks. The device (see figure) includes an electrochemical sensor, the output potential of which is proportional to the partial pressure of oxygen. The output of the sensor is amplified and fed to the input of a comparator circuit. A reference potential that corresponds to the amplified sensor output at the alarm oxygen-partial-pressure level is fed to the second input of the comparator. When the sensed partial pressure of oxygen falls below the minimum acceptable level, the output of the comparator goes from the low state (a few millivolts) to the high state (near the supply potential, which is typically 6.8 V for microphone power). The switching of the comparator output to the high state triggers a tactile alarm in the form of a vibration in the mask, generated by a small 1.3-Vdc pager motor spinning an eccentric mass at a rate between 8,000 and 10,000 rpm. The sensation of the mask vibrating against the crewmember s nose is very effective at alerting the crewmember, who may already be groggy from hypoxia and is immersed in an environment that is saturated with visual cues and sounds. Indeed, the sensation is one of rudeness, but such rudeness could be what is needed to stimulate the crewmember to take corrective action in a life-threatening situation.

Kelly, Mark↗
NASA NTRS2014

Statistical Modeling for Radiation Hardness Assurance

We cover the models and statistics associated with single event effects (and total ionizing dose), why we need them, and how to use them: What models are used, what errors exist in real test data, and what the model allows us to say about the DUT will be discussed. In addition, how to use other sources of data such as historical, heritage, and similar part and how to apply experience, physics, and expert opinion to the analysis will be covered. Also included will be concepts of Bayesian statistics, data fitting, and bounding rates.

Hardness Assurance↗
NASA NTRSDate not supplied

Adding GPU Support to the Markov Chain Monte Carlo Code Catmip

In geophysics, we are confronted with many under-determined inverse problems. For example, all of our observations of earthquakes are made at the Earth’s surface. So, when we try to infer how slip during an earthquake evolves in space and time, we find that there are many potential slip histories that are consistent with our limited observations and our understanding of earthquake physics. One way to approach these problems is with Bayesian analysis which allows us to infer the ensemble of all potential slip models that satisfy the observations and our prior knowledge of earthquake physics. In Bayesian analysis, our prior knowledge is known as the prior probability density function or prior PDF, the fit to the data is known as the data likelihood, and the target PDF that satisfies both the prior PDF and data likelihood is known as the posterior PDF. However, simulating the posterior PDF typically requires using Markov Chain Monte Carlo (MCMC) to draw tens of billions of random realizations of earthquake slip models, which may not be computationally feasible. To make this and similar geophysical inversions computationally tractable, we developed the Cascading Adaptive Transitional Metropolis In Parallel (CATMIP) algorithm. CATMIP is an efficient parallel Markov Chain Monte Carlo (MCMC) sampler that is used for model fitting and uncertainty quantification in geophysics. Example use cases are earthquake rupture modeling, determining mineral composition on Mars, reconstructing the history of ocean salinity, and historical earthquake relocation. CATMIP employs many parallel instances of the Metropolis algorithm for sampling in a transitioning framework. Transitioning is a process in which a set of random samples at equilibrium with a known probability density function (PDF) are used as seeds for the Markov chains to sample successive target PDFs that incrementally move the distribution from the starting seeds to the final desired PDF that describes the relative plausibility of potential values for the model parameters. The algorithm is implemented as a Master-Worker model employing MPI for communication. The worker processes are loosely coupled with global parameters periodically optimized by the master process. This provides a very high amount of parallelism with little communication between updates. During the presentation we will discuss the history of the algorithm and elaborate the earthquake rupture modeling use case for the CATMIP package. Our first step toward GPU optimization was to optimize the code for the CPU. CPU profiling revealed that most of the compute time is spent in calls to level 2 BLAS routines and calls to GSL random number generators. We revised the algorithm to employ level 3 BLAS routines instead. In our presentation we will describe how this was accomplished. Adding GPU support to CATMIP consisted mostly of replacing the calls to GSL with calls to GPU vendor-provided library routines. A small number of loops were directly implemented in CUDA. In the presentation will provide implementation details. Finally, we will discuss methods for profiling and opportunities for further optimizing GPU execution. By creating a code with the flexibility to run on either a CPU or GPU architecture, CATMIP can be used on systems ranging from large CPU-based HPC environments to single servers with GPU acceleration and everything in between.

HECC↗
NASA NTRS2022

A Robust Machine Learning Schema for Developing, Maintaining, and Disseminating Machine Learning Models

Recent advances in the development of machine learning (ML) algorithms have enabled the creation of predictive models that can improve decision making, decrease computational cost, and improve efficiency in a variety of fields. As an organization begins to develop and implement such models, the data used in the training, validation, and testing of ML models, the model parameters, and the use cases or limitations of the models must be properly stored to ensure models are both fully traceable and used correctly. In the context of predicting material behavior, advances in computationally intense, physics-based modeling of material behavior at various length scales and the emergence of Integrated Computational Materials Engineering (ICME) have driven the need for developing data-driven surrogate models of the physics-based simulation tools using ML techniques. Surrogate model development allows for accurate material behavior prediction at a fraction of the cost of its physics-based counterpart, allowing for multiscale simulations of real-world applications, further enabling the ability to design fit-for-purpose materials for a reasonable computational investment. However, training such models requires extensive data, and thus, effective data management is necessary to reach the full potential that ML can offer to material design and ICME. This paper proposes a generalized, robust schema that allows organizations to store both real (experimental) and virtual (simulation) data used to train ML models and the defining model parameters and architectures within the Granta MI Platform. The developed schema allows for various types of data inputs and outputs, including single point values, time-series data, and images that can be used in the prediction of material behavior, while following outlined best practices for effective data management. An effective schema for ML data and models can help prevent the recreation of virtual/real training data and surrogate models, help reduce the time to create new models similar to existing ones by offering a starting point in the hyperparameter determination stages, minimize resources devoted to verification and validation (V&V) and certification of models, and ensure that data and surrogate models are not misused due to full traceability of both the data and ML model. It also allows organizations access to models that have already been developed, such that they can be used in the design of new materials, enabling the overall goals of ICME.

Brandon L. Hearley↗
NASA NTRSDate not supplied

Predicting Fiber Failure of Plain Weave Fabric with Recursive Multiscale Micromechanics

Recent advances in the development of machine learning (ML) algorithms have enabled the creation of predictive models that can improve decision making, decrease computational cost, and improve efficiency in a variety of fields. As an organization begins to develop and implement such models, the data used in the training, validation, and testing of machine learning models, the model parameters, and the use cases or limitations of the models must be properly stored to ensure models are both fully traceable and used correctly. In the context of predicting material behavior, advances in computationally intense, physics-based, modeling of material behavior at various length scales, and the emergence of Integrated Computational Materials Engineering (ICME) have driven the need for developing data-driven surrogate models of the physics-based simulation tools using machine learning (ML) techniques. Surrogate model development allows for accurate material behavior prediction at a fraction of the cost of its physics-based counterpart, allowing for multiscale simulations of real-world applications, further enabling the ability to design fit-for-purpose materials for a reasonable computational investment. However, training such models requires extensive data, and thus effective data management is necessary to reach the full potential that ML can offer to material design and ICME. This paper proposes a generalized, robust schema that allows organizations to store both real (experimental) and virtual (simulation) data used to train machine learning models and the defining model parameters and architectures. The developed schema allows for various types of data inputs and outputs, including single point values, time-series data, and images that can be used in for various types of machine learning models while following outlined best practices for effective data management. An effective schema for machine learning data and models can help prevent the recreation of virtual/real training data and surrogate models, can help reduce the time to create new models similar to existing ones by offering a starting point in the hyperparameter determination stages, minimize resources devoted to verification and validation (V&V) and certification of models, and ensure that data and surrogate models are not misused due to full traceability of both the data and ML model. It also allows organizations access to models that have already been developed, such that they can be used in the design of new materials, enabling the overall goals of ICME.

Failure↗
DOE OSTI2023

How to identify different new neutrino oscillation physics scenarios at DUNE

Next generation neutrino oscillation experiments are expected to measure the remaining oscillation parameters with very good precision. They will have unprecedented capabilities to search for new physics that modify oscillations. DUNE, with its broad band beam, good particle identification, and relatively high energies will provide an excellent environment to search for new physics. If deviations from the standard three-flavor oscillation picture are seen however, it is crucial to know which new physics scenario is found so that it can be verified elsewhere and theoretically understood. We investigate several benchmark new physics scenarios by looking at existing long-baseline accelerator neutrino data from NOvA and T2K and determine at what sensitivity DUNE can differentiate among them. We consider sterile neutrinos and both vector and scalar non-standard neutrino interactions, all with new complex phases, the latter of which could conceivably provide absolute neutrino mass scale information. We find that, in many interesting cases, DUNE will have good model discrimination. We also perform a new fit to NOvA and T2K data with scalar NSI.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2020

The Completed SDSS-IV extended Baryon Oscillation Spectroscopic Survey: exploring the halo occupation distribution model for emission line galaxies

We study the modelling of the halo occupation distribution (HOD) for the eBOSS DR16 emission line galaxies (ELGs). Motivated by previous theoretical and observational studies, we consider different physical effects that can change how ELGs populate haloes. We explore the shape of the average HOD, the fraction of satellite galaxies, their probability distribution function (PDF), and their density and velocity profiles. Our baseline HOD shape was fitted to a semi-analytical model of galaxy formation and evolution, with a decaying occupation of central ELGs at high halo masses. We consider Poisson and sub/super-Poissonian PDFs for satellite assignment. We model both Navarro–Frenk–White and particle profiles for satellite positions, also allowing for decreased concentrations. We model velocities with the virial theorem and particle velocity distributions. Additionally, we introduce a velocity bias and a net infall velocity. We study how these choices impact the clustering statistics while keeping the number density and bias fixed to that from eBOSS ELGs. The projected correlation function, w p , captures most of the effects from the PDF and satellites profile. The quadrupole, ξ 2 , captures most of the effects coming from the velocity profile. We find that the impact of the mean HOD shape is subdominant relative to the rest of choices. Here, we fit the clustering of the eBOSS DR16 ELG data under different combinations of the above assumptions. The catalogues presented here have been analysed in companion papers, showing that eBOSS RSD+BAO measurements are insensitive to the details of galaxy physics considered here. These catalogues are made publicly available.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2024

Methods for Incorporating Model Uncertainty into Exoplanet Atmospheric Analysis

A key goal of exoplanet spectroscopy is to measure atmospheric properties, such as abundances of chemical species, in order to connect them to our understanding of atmospheric physics and planet formation. In this new era of high-quality JWST data, it is paramount that these measurement methods are robust. When comparing atmospheric models to observations, multiple candidate models may produce reasonable fits to the data. Typically, conclusions are reached by selecting the best-performing model according to some metric. This ignores model uncertainty in favor of specific model assumptions, potentially leading to measured atmospheric properties that are overconfident and/or incorrect. In this paper, we compare three ensemble methods for addressing model uncertainty by combining posterior distributions from multiple analyses: Bayesian model averaging, a variant of Bayesian model averaging using leave-one-out predictive densities, and stacking of predictive distributions. We demonstrate these methods by fitting the Hubble Space Telescope (HST) + Spitzer transmission spectrum of the hot Jupiter HD 209458b using models with different cloud and haze prescriptions. All of our ensemble methods lead to uncertainties on retrieved parameters that are larger but more realistic and consistent with physical and chemical expectations. Since they have not typically accounted for model uncertainty, uncertainties of retrieved parameters from HST spectra have likely been underreported. We recommend stacking as the most robust model combination method. Our methods can be used to combine results from independent retrieval codes and from different models within one code. They are also widely applicable to other exoplanet analysis processes, such as combining results from different data reductions.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2021

Analysis of TATB by uHPLC-DAD (V.2.2)

The following procedure describes the method for determining the purity of 1,3,5-triamino 2,4,6-trinitrobenzene (TATB) samples using a High-Performance Liquid Chromatography (HPLC) system fitted with a Diode Array Detector (DAD).

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2020

Predicting molecular dipole moments by combining atomic partial charges and atomic dipoles

The molecular dipole moment ( μ ) is a central quantity in chemistry. It is essential in predicting infrared and sum-frequency generation spectra as well as induction and long-range electrostatic interactions. Furthermore, it can be extracted directly—via the ground state electron density—from high-level quantum mechanical calculations, making it an ideal target for machine learning (ML). Here, we choose to represent this quantity with a physically inspired ML model that captures two distinct physical effects: local atomic polarization is captured within the symmetry-adapted Gaussian process regression framework which assigns a (vector) dipole moment to each atom, while the movement of charge across the entire molecule is captured by assigning a partial (scalar) charge to each atom. The resulting “MuML” models are fitted together to reproduce molecular μ computed using high-level coupled-cluster theory and density functional theory (DFT) on the QM7b dataset, achieving more accurate results due to the physics-based combination of these complementary terms. The combined model shows excellent transferability when applied to a showcase dataset of larger and more complex molecules, approaching the accuracy of DFT at a small fraction of the computational cost. We also demonstrate that the uncertainty in the predictions can be estimated reliably using a calibrated committee model. The ultimate performance of the models—and the optimal weighting of their combination—depends, however, on the details of the system at hand, with the scalar model being clearly superior when describing large molecules whose dipole is almost entirely generated by charge separation. These observations point to the importance of simultaneously accounting for the local and non-local effects that contribute to μ ; furthermore, they define a challenging task to benchmark future models, particularly those aimed at the description of condensed phases.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
NASA NTRS1995

EUVE observations of Algol: Detection of a continuum and implications for the coronal (Fe/H) abundance

We report results from the first extreme ultraviolet spectrum of the prototypical eclipsing binary Algol (beta Per), obtained with the spectrometers on the Extreme Ultraviolet Explorer (EUVE). The Algol spectrum in the 80-350 A range is dominated by emission lines of Fe XVI-XXIV, and the He II 304 A line. The Fe emission is characteristic of high-temperature plasma at temperatures up to at least log T approximately 7.3 K. We have successfully modeled the observed quiescent spectrum using a continuous emission measure distribution with the bulk of the emitting material at log T greater than 6.5. We are able to adequately fit both the coronal lines and continuum data with a cosmic abundance plasma, but only if Algol's quiescent corona is dominated by material at log T greater than 7.5, which is physically ruled out by prior X-ray observations of the quiescent Algol spectrum. Since the coronal (Fe/H) abundance is the principal determinant of the line-to-continuum ratio in the EUV, allowing the abundance to be a free parameter results in models with a range of best-fit abundances approximately = 15%-40% of solar photospheric (Fe/H). Since Algol's photospheric (Fe/H) appears to be near-solar, the anomalous EUV line-to-continuum ratio could either be the result of element segregation in the coronal formation process, or other, less likely mechanisms that may enhance the continuum with respect to the lines.

Stern, Robert A.↗
NASA NTRSDate not supplied

A Preliminary Assessment of Physical Demand during Simulated Lunar Surface Extravehicular Activities

Returning to the moon requires many advances in current space technology. One major aspect of this development is a new exploration spacesuit (xEMU). Taking lessons learned from Apollo era suitsand the Extravehicular Mobility Unit (EMU) used on the International Space Station (ISS), xEMU will have increased mobility, dust mitigation, headspace, glove fit, and life support capabilities. Artemis astronauts in xEMU will complete a far more rigorous Extravehicular Activity (EVA) schedule than Apolloand ISS. Notably, metabolic rates during Apollo lunar EVA tasks were observed to be up to 50% lower than similar tasks performed in a ground analog environment under simulated partial gravity with newer suits. Therefore, understanding the physical demands of lunar surface exploration operations is criticalto ensuring best outcomes operating within the constraints of xEMU and planning for exploration EVA activities. This study utilized the Active Response Gravity Offload System (ARGOS) to simulate the lunar environment and continuously offload subjects to lunar gravity. Two male subjects completed two days of EVAs wearing the pressurized Mark III spacesuit, completing suit fit and mobility checks, as well as simulated lander operations, cable routing, crew rescue, geology, payload relocation, and traverse tasks in an end-to-end EVA (E2E) task block and standalone (SA) task blocks. We recorded continuous values of metabolic rate (MR) and heart rate (HR) to assess physical demand. During the E2E task block, subjects did not rest between tasks to simulate continuous effort from task to task, as in real EVAs. In comparison, subjects had a 5-minute break after each SA task block to allow for the metabolic rate and heart rate to return to baseline.MR values were categorized as low (≤ 700 BTU/hr), medium (700-1000 BTU/HR), and high (≥ 1000 BTU/hr), while HR values were categorized as low (≤150) and high (>150). During the 16 tasks in the E2E block, subjects averaged low MR in 6% of tasks, medium MR in 47% of tasks, and high MR in 47% of tasks. While MR was consistent between subjects, Subject 1 averaged low HR for 100% of these tasks, while Subject 2 averaged low HR in 44% of tasks. During the 23 tasks in the SA task blocks, subjects averaged low MR in 26% of tasks, medium MR in 52% of tasks, and high MR in 22% of tasks. Again, HR was different between subjects, with subject 1 averaging low HR in 100% of these tasks while subject 2 averaged low HR in 70%. Across all tasks in this study, subjects reached maximum MR and HR values during a 500m traverse at 30% grade in the E2E block (subject 1: 1747 BTU/hr, 150 BPM; subject 2: 1656 BTU/hr, 177 BPM).Understanding the physical demand to complete exploration EVA tasks will be instrumental to the future success of exploration spacesuit designs and missions. Further work in this study will be needed to characterize MR during exploration EVA tasks, including expanding the subject pool and testing new suit designs.

Taylor E Schlotman↗
NASA NTRSDate not supplied

Physics Informed Neural Nets for Systems Health Management

To facilitate and solve the prediction problem, awareness of the current health state of the system is key, since it is necessary to perform condition-based predictions. To accurately predict the future state of any system, it is required to possess knowledge of its current health state and future operational conditions. Development in data-driven algorithms in regression of complex nonlinear functions and classification tasks have generated a growing interest in artificial intelligence for industrial applications. Complex multi-physics models as well as digital twins, once purely built on physics and corresponding simplified lumped parameter iterations, can now benefit from machine learning algorithms to mitigate the lack of understanding of some complex behavior. The research work presents application of physics-informed neural nets application to a representative electric powertrain for unmanned aerial vehicles. The model is composed of physics-derived and empirical equations, integrated with connected networks that are strategically placed within the model to substitute equations that are subject to large uncertainty. Polynomial fit driven by heuristics or empirical observations can be substituted by more flexible networks that can minimize the error between model predictions and observations without being restricted to a predefined functional form. This modeling strategy allows training of networks deep inside the model and unknown parameters in a single learning stage.

Physics Informed↗
NASA NTRSDate not supplied

Model Based Approaches for Fault Detection, Prognostics, Decision Making in Complex Systems

The presentation discusses application of model based approaches to complex systems. The model is composed of physics-derived and empirical equations, integrated with connected networks that are strategically placed within the model to substitute equations that are subject to large uncertainty. Polynomial fit driven by heuristics or empirical observations can be substituted by more flexible networks that can minimize the error between model predictions and observations without being restricted to a predefined functional form. This modeling strategy allows training of networks deep inside the model and unknown parameters in a single learning stage.

Physics Informed↗